PixelCNN

Closed weights Google DeepMind June 2016

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Google DeepMind
Organisation type
Industry
Country
United States of America
Published
16 June 2016
Authors
Aaron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, Koray Kavukcuoglu

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image generation

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
15,728,640,000 tokens

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Chips used
32
Wall-clock time
60 hours

We were able to achieve similar performance to the PixelRNN (Row LSTM [30]) in less than half the training time (60 hours using 32 GPUs).

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited,SOTA improvement

Best performance on NLL test.

Record confidence
Unknown
Citations
3,079

Sources

Where this record came from and when it was last checked.

Reference
Conditional Image Generation with PixelCNN Decoders
Last updated
28 November 2025

What the numbers mean

About this model

PixelCNN was published by Google DeepMind, in United States of America, in June 2016. The organisation is categorised as industry.

It works in Vision, and is recorded as doing image generation.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

What went into building it

Around 15,728,640,000 tokens went into training it.

The reason it appears in this catalogue at all is highly cited,SOTA improvement.

Answers

PixelCNN — common questions

01

What GPU do I need to run PixelCNN?

None. PixelCNN is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

Is PixelCNN open source?

The licensing for PixelCNN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

How many parameters does PixelCNN have?

No parameter count has been published for PixelCNN, which is why no memory or speed figure appears on this page.

04

Who created PixelCNN?

PixelCNN was published by Google DeepMind, based in United States of America, categorised as industry.

05

When was PixelCNN released?

PixelCNN was published in June 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is PixelCNN used for?

PixelCNN works in Vision, and is recorded as handling image generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.